# Jina AI (MCP Server)

> Read URLs, search the web and arXiv, rerank and dedupe with Jina AI

- Type: MCP server
- Publisher: Jina AI (official)
- Categories: Research, AI & ML
- Website: https://github.com/jina-ai/MCP
- Source: https://github.com/jina-ai/MCP
- Transport: streamable-http
- Server URL: https://mcp.jina.ai/v1
- Sign-in: api-key
- Environment variables: JINA_API_KEY
- GitHub stars: 869
- Listed: 2025-08-09

## About

Jina AI's official remote MCP server exposes its Reader, Search, Embeddings and Reranker APIs. Tools cover web, arXiv, SSRN and image search, URL reading and screenshots, PDF extraction, reranking and deduplication. A Jina API key is optional for some tools and required for others.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.jina.ai/v1 as the MCP server URL. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add jina-ai --url https://mcp.jina.ai/v1 --bearer-token-env-var JINA_API_KEY
   ```

   config.toml:

   ```toml
   [mcp_servers.jina-ai]
   url = "https://mcp.jina.ai/v1"
   bearer_token_env_var = "JINA_API_KEY"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "jina_ai",
           "server_url": "https://mcp.jina.ai/v1",
           "authorization": os.environ["JINA_API_KEY"],
           "require_approval": "never",
       }],
       input="Read this URL and give me clean markdown",
   )
   print(response.output_text)
   ```

## Tools

- `read_url`
- `parallel_read_url`
- `capture_screenshot_url`
- `search_web`
- `parallel_search_web`
- `search_arxiv`
- `search_ssrn`
- `search_images`
- `extract_pdf`
- `sort_by_relevance`
- `deduplicate_strings`
- `guess_datetime_url`

## Example prompts

- "Read this URL and give me clean markdown"
- "Search arXiv for recent papers on speculative decoding"
- "Rerank these 20 snippets by relevance to my question"
- "Take a screenshot of this web page"

## Related

- [Browser Use](https://chatgptplugins.directory/mcp/browser-use.md): Run Browser Use cloud browser agents or control a local browser over MCP
- [Memory](https://chatgptplugins.directory/mcp/memory.md): Knowledge graph-based persistent memory across conversations
- [Mem0](https://chatgptplugins.directory/mcp/mem0.md): Hosted long-term memory for AI agents and clients
- [Sequential Thinking](https://chatgptplugins.directory/mcp/sequential-thinking.md): Structured, reflective step-by-step problem solving for LLMs
- [Fetch](https://chatgptplugins.directory/mcp/fetch.md): Fetch web pages and convert them to markdown for LLMs
- [Serena](https://chatgptplugins.directory/mcp/serena.md): Semantic code retrieval and editing toolkit for coding agents

---
Source: https://chatgptplugins.directory/mcp/jina-ai · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.